metadata
tags:
- generated_from_trainer
model-index:
- name: calculator_model_test
results: []
calculator_model_test
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0868
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.9639 | 1.0 | 6 | 2.2327 |
2.0112 | 2.0 | 12 | 1.7195 |
1.5448 | 3.0 | 18 | 1.3346 |
1.2344 | 4.0 | 24 | 1.1502 |
1.0961 | 5.0 | 30 | 1.0083 |
0.9938 | 6.0 | 36 | 0.9712 |
0.9205 | 7.0 | 42 | 0.8846 |
0.8293 | 8.0 | 48 | 0.7529 |
0.7735 | 9.0 | 54 | 0.7236 |
0.7284 | 10.0 | 60 | 0.7006 |
0.673 | 11.0 | 66 | 0.6580 |
0.6238 | 12.0 | 72 | 0.5931 |
0.5871 | 13.0 | 78 | 0.5475 |
0.548 | 14.0 | 84 | 0.4944 |
0.5 | 15.0 | 90 | 0.4888 |
0.4772 | 16.0 | 96 | 0.4259 |
0.4605 | 17.0 | 102 | 0.4471 |
0.4191 | 18.0 | 108 | 0.3692 |
0.3724 | 19.0 | 114 | 0.3329 |
0.3483 | 20.0 | 120 | 0.3270 |
0.3268 | 21.0 | 126 | 0.2739 |
0.2884 | 22.0 | 132 | 0.2396 |
0.2567 | 23.0 | 138 | 0.2038 |
0.2415 | 24.0 | 144 | 0.2121 |
0.2322 | 25.0 | 150 | 0.1778 |
0.1971 | 26.0 | 156 | 0.1631 |
0.2065 | 27.0 | 162 | 0.1592 |
0.1918 | 28.0 | 168 | 0.1422 |
0.1854 | 29.0 | 174 | 0.1359 |
0.1691 | 30.0 | 180 | 0.1291 |
0.1645 | 31.0 | 186 | 0.1201 |
0.1614 | 32.0 | 192 | 0.1138 |
0.1435 | 33.0 | 198 | 0.1082 |
0.1354 | 34.0 | 204 | 0.1014 |
0.129 | 35.0 | 210 | 0.0956 |
0.1298 | 36.0 | 216 | 0.0971 |
0.1266 | 37.0 | 222 | 0.0916 |
0.1374 | 38.0 | 228 | 0.0919 |
0.1217 | 39.0 | 234 | 0.0882 |
0.1341 | 40.0 | 240 | 0.0868 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2